This paper proposes a subpixel transformation method to correct Keystone and Smile distortions in fiber spectral images from the Fiber Arrayed Solar Optical Telescope.These distortions affect the spatial and spectral ...This paper proposes a subpixel transformation method to correct Keystone and Smile distortions in fiber spectral images from the Fiber Arrayed Solar Optical Telescope.These distortions affect the spatial and spectral positions,degrading resolution and accuracy.To correct Keystone distortion,we use a local summation and peak-finding method to locate central horizontal coordinates,calculate shifting values,and straighten the curves.For Smile distortion,we use quartic polynomial fitting based on absorption lines at different wavelengths.This technique preserves subpixel components,redistributes pixel values,and interpolates non-fiber portions,rectifying the spectra for accurate analysis.The method can also be applied to other astronomical projects like Large Sky Area Multi-Object Fiber Spectroscopic Telescope,enhancing the accuracy and reliability of spectral data in various astronomical studies.展开更多
Astronomical spectra are vital for deriving stellar properties,yet low signal-to-noise ratio(SNR)spectra often obscure key features,complicating accurate analysis.This study presents spec-Diffusion Probabilistic Model...Astronomical spectra are vital for deriving stellar properties,yet low signal-to-noise ratio(SNR)spectra often obscure key features,complicating accurate analysis.This study presents spec-Diffusion Probabilistic Models(DDPM),a novel deep learning approach based on DDPM,aimed at denoising low SNR spectra to improve stellar parameter estimation.Leveraging the LAMOST DR10 data set,we developed spec-DDPM using a tailored U-Net architecture(spec-Unet)to iteratively predict and remove noise.The model was trained on 28,500 low and high SNR spectral pairs and benchmarked against conventional methods,including Principal Component Analysis,wavelet techniques,and a modified DnCNN model.The spec-DDPM demonstrated superior performance,with reduced Mean Absolute Error,elevated Structural Similarity Index Measure,and enhanced spectral loss metrics.It effectively preserved critical spectral features and corrected continuum distortions.Validation experiments further confirmed its ability to improve stellar parameter estimation with reduced errors.These results underscore spec-DDPM’s potential to elevate spectral data quality,offering applications in restoring defective spectra and refining large-scale astronomical surveys.This work highlights the transformative role of deep learning in astronomical data processing.展开更多
After numerous sky survey devices such as Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST)were put into use,astronomical research officially entered a new era of explosive data growth.Massive amounts ...After numerous sky survey devices such as Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST)were put into use,astronomical research officially entered a new era of explosive data growth.Massive amounts of data make the theoretical research on stellar evolution simple,but they bring huge challenges to the task of spectral classification.In order to classify celestial spectra faster and better,we need to borrow the tool of deep learning.In the field of traditional stellar spectral classification,Convolutional Neural Network(CNN)is mostly used as the feature extraction module to extract stellar spectral features.CNN extracts the local features of spectral data through convolution operations,eliminates redundant information,and compresses the data in a maximized pooling manner.However,the fully connected layer of CNN does not have an effective long-range dependent feature extraction function.The sliding window local attention mechanism of the Swin Transformer enables information interaction between the collected adjacent Windows,demonstrating the correlation of spectral lines at different wavelengths.The global modeling ability of the sliding window also enables the extracted features to start from the full spectrum,ensuring the integrity of the spectral information.Meanwhile,the Swin Transformer retains the characteristics of multi-scale feature extraction of CNN.Different receptive fields can obtain both the features of narrow spectral lines and those of wide spectral lines.Therefore,based on the Swin Transformer model,we have built the Swin Transformer-ResNet-DenseNet(StRD)automatic classification algorithm for stellar spectra.The algorithm consists of four parts:(1)Data pre-processing;(2)Feature extraction from the data;(3)Model modification;(4)Automatic classification.Feature extraction forms the core of the StRD algorithm.The extracted data reflects the correlation of spectral lines at different wavelengths of the stellar spectrum and captures multi-scale features.When the StRD algorithm is used to automatically classify the spectra of A,B,dM,F,G,gM and K type stars with an R-band signal-to-noise ratio greater than 30,the classification accuracy is 0.98.This is higher than the classification accuracies of the CNN+Bayes,CNN+KNN,CNN+SVM,CNN+Adaboost and CNN+RF algorithms:0.862,0.876,0.894,0.868 and 0.889 respectively.展开更多
Compared to high-resolution spectra,low-resolution spectra offer higher observational efficiency and broader sky coverage,making them especially valuable for large-scale stellar surveys.The Large Sky Area Multi-Object...Compared to high-resolution spectra,low-resolution spectra offer higher observational efficiency and broader sky coverage,making them especially valuable for large-scale stellar surveys.The Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST)survey alone has collected tens of millions of low-resolution stellar spectra,providing an unprecedented opportunity for large-scale stellar parameter estimation.However,a substantial portion of these spectra suffer from low signal-to-noise ratio(low-SNR),which poses significant challenges for accurate parameter determination.Accurately extracting stellar atmospheric parameters from such data can significantly enhance the utility of spectral observations.However,these low-SNR spectra often introduce considerable uncertainty in parameter estimation.To address this issue,we propose a novel method based on the Cycle-Consistent Convolutional Neural Network(Cycle-CNN)for predicting key stellar atmospheric parameters,including effective temperature(T_(eff)),surface gravity(log g),and metallicity([Fe/H]).This method integrates the cycle-consistency learning mechanism of Cycle-GAN with the strong modeling capability of CNNs,thereby improving model robustness and reducing prediction uncertainty under low-SNR conditions.We train and evaluate the model on spectra from LAMOST DR9 across different SNR intervals(2-15).For spectra with SNR between 10 and 15,the model achieves prediction accuracies of 63.22 K for T_(eff),0.11 dex for log g,and 0.07 dex for[Fe/H].For the spectra with SNR between 5 and 10,the prediction accuracies are 89.45 K,0.17 dex,and 0.11 dex,respectively.Even under extreme conditions with SNR between 2 and 5 and limited data availability,the model maintains good performance,achieving accuracies of 145.36 K,0.29 dex,and 0.18 dex.Furthermore,we validate our predictions against reference parameters from high-resolution surveys,and the results demonstrate good consistency with other large-scale spectroscopic surveys.These findings indicate that the proposed Cycle-CNN method can provide stable and accurate predictions of atmospheric parameters even under low-quality spectral conditions,offering a reliable solution to improve the scientific utilization of low-quality spectra.展开更多
The derivation of element abundances of stars is a key step in detailed spectroscopic analysis. A spectroscopic method may suffer from errors associated with model simplifications. We have developed a new method of de...The derivation of element abundances of stars is a key step in detailed spectroscopic analysis. A spectroscopic method may suffer from errors associated with model simplifications. We have developed a new method of deriving the various element abundances of stars based on the calibration established from a group of standard stars. We perform principal component analysis (PCA) on a homogeneous library of stellar spectra, and then use machine learning to calibrate the relationship between principal components and element abundances. By testing with spectral libraries S4N and MILES, we find that our procedure provides good consistency when spectra from a homogeneous set of observations are used, and it could be expanded to stars with quite a wide range of stellar parameters, with both dwarfs and giants. Moreover, we discuss the four key factors that have a significant impact on the results of derived element abundances, including the resolution of the spectra, wavelength range, the signal-to-noise ratio (S/N) of spectra and the number of principal components adopted.展开更多
Long-term spectroscopic monitoring campaigns on active galactic nuclei(AGNs)provide a wealth of information about its interior structure and kinematics.However,a number of the observations suffer from the contaminatio...Long-term spectroscopic monitoring campaigns on active galactic nuclei(AGNs)provide a wealth of information about its interior structure and kinematics.However,a number of the observations suffer from the contamination of second-order spectra(SOS)which will introduce some undesirable uncertainties at the red side of the spectra.In this paper,we test the effect of SOS and propose a method to correct it in the time domain spectroscopic data using the simultaneously observed comparison stars.Based on the reverberation mapping(RM)data of NGC 5548 in2019,one of the most intensively monitored AGNs by the Lijiang 2.4 m telescope,we find that the scientific object,comparison star,and spectrophotometric standard star can jointly introduce up to~30%SOS for Grism 14.This irregular but smooth SOS significantly affects the flux density and profile of the emission line,while having little effect on the light curve.After applying our method to each spectrum,we find that the SOS can be corrected effectively.The deviation between corrected and intrinsic spectra is~2%,and the impact of SOS on time lag is very minor.This method makes it possible to obtain the HαRM measurements from archival data provided that the spectral shape of the AGN under investigation does not have a large change.展开更多
基金Astronomy Joint Research Fund supported this work under cooperative agreements between the National Natural Science Foundation of China(NSFC)and the Chinese Academy of Sciences(CAS)(project numbers:U2031132 and U1931206).
文摘This paper proposes a subpixel transformation method to correct Keystone and Smile distortions in fiber spectral images from the Fiber Arrayed Solar Optical Telescope.These distortions affect the spatial and spectral positions,degrading resolution and accuracy.To correct Keystone distortion,we use a local summation and peak-finding method to locate central horizontal coordinates,calculate shifting values,and straighten the curves.For Smile distortion,we use quartic polynomial fitting based on absorption lines at different wavelengths.This technique preserves subpixel components,redistributes pixel values,and interpolates non-fiber portions,rectifying the spectra for accurate analysis.The method can also be applied to other astronomical projects like Large Sky Area Multi-Object Fiber Spectroscopic Telescope,enhancing the accuracy and reliability of spectral data in various astronomical studies.
基金study was Foundation of China(NSFC)under grant Nos.11873037 and 11803016the science research grants from the China Manned Space Project with Nos.CMS-CSST-2021-B05 and CMSCSST-2021-A08+1 种基金the Natural Science Foundation of Shandong Province under grant Nos.ZR2022MA076,ZR2022MA089 and ZR2024MA063the Young Scholars Program of Shandong University,Weihai,under grant No.2016WHWLJH09 and GHfund A(202202018107).
文摘Astronomical spectra are vital for deriving stellar properties,yet low signal-to-noise ratio(SNR)spectra often obscure key features,complicating accurate analysis.This study presents spec-Diffusion Probabilistic Models(DDPM),a novel deep learning approach based on DDPM,aimed at denoising low SNR spectra to improve stellar parameter estimation.Leveraging the LAMOST DR10 data set,we developed spec-DDPM using a tailored U-Net architecture(spec-Unet)to iteratively predict and remove noise.The model was trained on 28,500 low and high SNR spectral pairs and benchmarked against conventional methods,including Principal Component Analysis,wavelet techniques,and a modified DnCNN model.The spec-DDPM demonstrated superior performance,with reduced Mean Absolute Error,elevated Structural Similarity Index Measure,and enhanced spectral loss metrics.It effectively preserved critical spectral features and corrected continuum distortions.Validation experiments further confirmed its ability to improve stellar parameter estimation with reduced errors.These results underscore spec-DDPM’s potential to elevate spectral data quality,offering applications in restoring defective spectra and refining large-scale astronomical surveys.This work highlights the transformative role of deep learning in astronomical data processing.
基金supported by the Astronomy Joint Fund of the National Natural Science Foundation of China(U1731128).
文摘After numerous sky survey devices such as Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST)were put into use,astronomical research officially entered a new era of explosive data growth.Massive amounts of data make the theoretical research on stellar evolution simple,but they bring huge challenges to the task of spectral classification.In order to classify celestial spectra faster and better,we need to borrow the tool of deep learning.In the field of traditional stellar spectral classification,Convolutional Neural Network(CNN)is mostly used as the feature extraction module to extract stellar spectral features.CNN extracts the local features of spectral data through convolution operations,eliminates redundant information,and compresses the data in a maximized pooling manner.However,the fully connected layer of CNN does not have an effective long-range dependent feature extraction function.The sliding window local attention mechanism of the Swin Transformer enables information interaction between the collected adjacent Windows,demonstrating the correlation of spectral lines at different wavelengths.The global modeling ability of the sliding window also enables the extracted features to start from the full spectrum,ensuring the integrity of the spectral information.Meanwhile,the Swin Transformer retains the characteristics of multi-scale feature extraction of CNN.Different receptive fields can obtain both the features of narrow spectral lines and those of wide spectral lines.Therefore,based on the Swin Transformer model,we have built the Swin Transformer-ResNet-DenseNet(StRD)automatic classification algorithm for stellar spectra.The algorithm consists of four parts:(1)Data pre-processing;(2)Feature extraction from the data;(3)Model modification;(4)Automatic classification.Feature extraction forms the core of the StRD algorithm.The extracted data reflects the correlation of spectral lines at different wavelengths of the stellar spectrum and captures multi-scale features.When the StRD algorithm is used to automatically classify the spectra of A,B,dM,F,G,gM and K type stars with an R-band signal-to-noise ratio greater than 30,the classification accuracy is 0.98.This is higher than the classification accuracies of the CNN+Bayes,CNN+KNN,CNN+SVM,CNN+Adaboost and CNN+RF algorithms:0.862,0.876,0.894,0.868 and 0.889 respectively.
基金supported by the Natural Science Foundation of Shandong Province(Nos.ZR2022MA076 and ZR2024MA063)the National Natural Science Foundation of China(NSFC,grant Nos.11873037,U1931209,11803016)+2 种基金the science research grants from the China Manned Space Project with No.CMSCSST-2021-B05 and CMS-CSST-2021-A08supported by the Doctoral Research Foundation of Shandong Technology and Business University(grant No.306519)the Young Scholars Program of Shandong University,Weihai(2016WHWLJH09)。
文摘Compared to high-resolution spectra,low-resolution spectra offer higher observational efficiency and broader sky coverage,making them especially valuable for large-scale stellar surveys.The Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST)survey alone has collected tens of millions of low-resolution stellar spectra,providing an unprecedented opportunity for large-scale stellar parameter estimation.However,a substantial portion of these spectra suffer from low signal-to-noise ratio(low-SNR),which poses significant challenges for accurate parameter determination.Accurately extracting stellar atmospheric parameters from such data can significantly enhance the utility of spectral observations.However,these low-SNR spectra often introduce considerable uncertainty in parameter estimation.To address this issue,we propose a novel method based on the Cycle-Consistent Convolutional Neural Network(Cycle-CNN)for predicting key stellar atmospheric parameters,including effective temperature(T_(eff)),surface gravity(log g),and metallicity([Fe/H]).This method integrates the cycle-consistency learning mechanism of Cycle-GAN with the strong modeling capability of CNNs,thereby improving model robustness and reducing prediction uncertainty under low-SNR conditions.We train and evaluate the model on spectra from LAMOST DR9 across different SNR intervals(2-15).For spectra with SNR between 10 and 15,the model achieves prediction accuracies of 63.22 K for T_(eff),0.11 dex for log g,and 0.07 dex for[Fe/H].For the spectra with SNR between 5 and 10,the prediction accuracies are 89.45 K,0.17 dex,and 0.11 dex,respectively.Even under extreme conditions with SNR between 2 and 5 and limited data availability,the model maintains good performance,achieving accuracies of 145.36 K,0.29 dex,and 0.18 dex.Furthermore,we validate our predictions against reference parameters from high-resolution surveys,and the results demonstrate good consistency with other large-scale spectroscopic surveys.These findings indicate that the proposed Cycle-CNN method can provide stable and accurate predictions of atmospheric parameters even under low-quality spectral conditions,offering a reliable solution to improve the scientific utilization of low-quality spectra.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11890694 and 11390371)
文摘The derivation of element abundances of stars is a key step in detailed spectroscopic analysis. A spectroscopic method may suffer from errors associated with model simplifications. We have developed a new method of deriving the various element abundances of stars based on the calibration established from a group of standard stars. We perform principal component analysis (PCA) on a homogeneous library of stellar spectra, and then use machine learning to calibrate the relationship between principal components and element abundances. By testing with spectral libraries S4N and MILES, we find that our procedure provides good consistency when spectra from a homogeneous set of observations are used, and it could be expanded to stars with quite a wide range of stellar parameters, with both dwarfs and giants. Moreover, we discuss the four key factors that have a significant impact on the results of derived element abundances, including the resolution of the spectra, wavelength range, the signal-to-noise ratio (S/N) of spectra and the number of principal components adopted.
基金funded by the National Key R&D Program of China with No.2021YFA1600404the National Natural Science Foundation of China(NSFC+6 种基金grant Nos.11991051,12303022,12373018,12203096,12103041,12073068)Yunnan Fundamental Research Projects(grant Nos.202301AT070339,202301AT070358)Yunnan Postdoctoral Foundation Funding Project,the Yunnan Province Foundation(202001AT070069)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(2022058)the Topnotch Young Talents Program of Yunnan Province,Special Research Assistant Funding Project of Chinese Academy of Sciencesthe science research grants from the China Manned Space Project with No.CMS-CSST-2021-A06Funding for the telescope has been provided by the Chinese Academy of Sciences and the People’s Government of Yunnan Province。
文摘Long-term spectroscopic monitoring campaigns on active galactic nuclei(AGNs)provide a wealth of information about its interior structure and kinematics.However,a number of the observations suffer from the contamination of second-order spectra(SOS)which will introduce some undesirable uncertainties at the red side of the spectra.In this paper,we test the effect of SOS and propose a method to correct it in the time domain spectroscopic data using the simultaneously observed comparison stars.Based on the reverberation mapping(RM)data of NGC 5548 in2019,one of the most intensively monitored AGNs by the Lijiang 2.4 m telescope,we find that the scientific object,comparison star,and spectrophotometric standard star can jointly introduce up to~30%SOS for Grism 14.This irregular but smooth SOS significantly affects the flux density and profile of the emission line,while having little effect on the light curve.After applying our method to each spectrum,we find that the SOS can be corrected effectively.The deviation between corrected and intrinsic spectra is~2%,and the impact of SOS on time lag is very minor.This method makes it possible to obtain the HαRM measurements from archival data provided that the spectral shape of the AGN under investigation does not have a large change.
